News for hackers. Stuff that matters.
Re:NeuralTalk2: Efficient Image Captioning code in Torch, ru... by gabipurcaru on Sunday November 22, 2015 @06:02PM (#10611897)
Is there a way to let the algorithm not make a guess if it doesn't find a strong match? I guess it would be better to not output anything than to output gibberish, right?

There are no comments on this comment yet.